Deep layered convolutional neural networks form a basis for building Cognitive Computing architectures which can be trained and adapted to different sensory recognition tasks. In order to define and implement efficient scalable network architectures, two aspects need to be particularly investigated, namely appropriate design principles for the architectural layout and learning mechanisms for layers of hierarchical feature detectors and their combination. Regarding such principles, mechanisms of, e.g., reinforcement learning and evolutionary computation will be investigated for non-local optimization of network architectures and their components in conjunction with local learning of feature representations.
In this dissertation project the activation dynamics during information processing in recurrent convolutional networks will be investigated with a special focus on how information is integrated over time. To this end, canonical network principles will be identified and analyzed. For example, convolutional networks will utilize a simplified model of a cortical column (to serve as a computational unit or building block) and its interaction with other units in layered architectures of feedforward and feedback interaction. The individual representations of such layered networks will be learned by principles of hierarchical learning to build deep networks relying on principles of modified local Hebbian learning and global modulating reinforcer signals. An evaluation of such network architectures will utilize benchmark datasets, such as, e.g., MNIST, CIFAR, or object recognition challenges.
Supervisor and assignment
Direct supervisor
Prof. Dr. Heiko Neumann, Institute of Neural Information Processing, Ulm University
Tandem partner
Prof. Dr. Christian Schlegel, Institute of Computer Science (real-time systems, service robotics), Ulm University of Applied Sciences
Expert advisors
Prof. Dr. Susanne Biundo-Stephan, Institute of Artificial Intelligence, Ulm University
Assigned to: | Ulm University |
Methods/technologies:
Applications:
| perception
service robotics
|
Contact
For questions regarding the Post Graduate School of Ulm University and Ulm University of Applied Sciences, "Cognitive Computing in Socio-Technical Systems", please contact the project leaders Prof. Dr. Manfred Reichert and Prof. Dr. Christian Schlegel.
Project leaders
Prof. Dr. Christian Schlegel
Ulm University of Applied Sciences
Department of Computer Science
Prof. Dr. Manfred Reichert
Ulm University
Institute of Databases and Information Systems
Information from Ulm University about the Post Graduate School of Ulm University and Ulm University of Applied Sciences
Applications
Application guidelines
Invitation for applications
Application form